Application of Feature Transformation and Learning Methods in Phoneme Classification

This paper examines the applicability of some learning techniques to the classification of phonemes. The methods tested were artificial neural nets (ANN), support vector machines (SVM) and Gaussian mixture modeling. We compare these methods with a traditional hidden Markov phoneme model (HMM) working with the linear prediction-based cepstral coefficient features (LPCC). We also tried to combine the learners with feature transformation methods, like linear discriminant analysis (LDA), principal component analysis (PCA) and independent component analysis (ICA). We found that the discriminative learners can attain the efficiency of the HMM, and after LDA they can attain practically the same score on only 27 features. PCA and ICA proved ineffective, apparently because of the discrete cosine transform inherent in LPCC.

[1]  János Csirik,et al.  A Comparative Study of Several Feature Transformation and Learning Methods for Phoneme Classification , 2000, Int. J. Speech Technol..

[2]  Vladimir Vapnik,et al.  Statistical learning theory , 1998 .

[3]  Máté Szarvas,et al.  Automatic Recognition of Hungarian: Theory And Practice , 2000, Int. J. Speech Technol..

[4]  Steven Greenberg,et al.  The modulation spectrogram: in pursuit of an invariant representation of speech , 1997, 1997 IEEE International Conference on Acoustics, Speech, and Signal Processing.

[5]  José A. R. Fonollosa,et al.  Feature decorrelation methods in speech recognition. a comparative study , 1998, ICSLP.

[6]  László Tóth,et al.  A Discriminative Segmental Speech Model and Its Application to Hungarian Number Recognition , 2000, TSD.

[7]  Pierre Comon Independent component analysis - a new concept? signal processing , 1994 .

[8]  Aapo Hyvärinen,et al.  New Approximations of Differential Entropy for Independent Component Analysis and Projection Pursuit , 1997, NIPS.

[9]  G. McLachlan,et al.  Pattern Classification: A Unified View of Statistical and Neural Approaches. , 1998 .

[10]  Jürgen Schürmann,et al.  Pattern classification , 2008 .

[11]  I. Jolliffe Principal Component Analysis , 2002 .

[12]  Pierre Comon,et al.  Independent component analysis, A new concept? , 1994, Signal Process..

[13]  A. Hyvarinen A family of fixed-point algorithms for independent component analysis , 1997, 1997 IEEE International Conference on Acoustics, Speech, and Signal Processing.

[14]  Richard O. Duda,et al.  Pattern classification and scene analysis , 1974, A Wiley-Interscience publication.

[15]  Biing-Hwang Juang,et al.  Fundamentals of speech recognition , 1993, Prentice Hall signal processing series.

[16]  László Tóth,et al.  An overview of the OASIS speech recognition project , 1999 .